Header

UZH-Logo

Maintenance Infos

Automated Detection of Mind Wandering: A Mobile Application


Cheetham, Marcus; Cepeda, Cátia; Gamboa, Hugo (2016). Automated Detection of Mind Wandering: A Mobile Application. In: Gilbert, James; Azhari, Haim; Hesham, Ali. Proceedings of the 9th International Joint Conference on Biomedical Engineering Systems and Technologies - (Volume 4). Setúbal: Scitepress, 198-205.

Abstract

There is growing interest in mindfulness-based training of attention. A particular challenge for novices is learning to sustain focused attention while ensuring that the mind does not wander. This paper presents the development of a tool for the automated detection of episodes of mind wandering (MW), on the basis of biosignals, while normal healthy participants engaged in brief mindfulness-based training (BMT) of attention. BMT required five 20-minute training sessions on consecutive days and entailed practice of breath-focused attention, a typical exercise in mindfulness-based techniques of stress-reduction. Heart rate, respiratory rate, electrodermal and electromyographic activity were measured, and participants pressed a button to indicate the subjective detection of MW during training. The data showed that BMT did not influence our measures of stress but BMT was effective in reducing the frequency of subjectively detected MW events. The algorithm for offline detection of MW achieved an accuracy of 85%. Based on this algorithm, a mobile application was developed for automated MW detection in real-time. The application requires the use of easily placeable sensors, provides a new approach to the real-time MW detection, and could be developed further for use in MW-related investigations and interventions (such as mindfulness-based training of focused attention).

Abstract

There is growing interest in mindfulness-based training of attention. A particular challenge for novices is learning to sustain focused attention while ensuring that the mind does not wander. This paper presents the development of a tool for the automated detection of episodes of mind wandering (MW), on the basis of biosignals, while normal healthy participants engaged in brief mindfulness-based training (BMT) of attention. BMT required five 20-minute training sessions on consecutive days and entailed practice of breath-focused attention, a typical exercise in mindfulness-based techniques of stress-reduction. Heart rate, respiratory rate, electrodermal and electromyographic activity were measured, and participants pressed a button to indicate the subjective detection of MW during training. The data showed that BMT did not influence our measures of stress but BMT was effective in reducing the frequency of subjectively detected MW events. The algorithm for offline detection of MW achieved an accuracy of 85%. Based on this algorithm, a mobile application was developed for automated MW detection in real-time. The application requires the use of easily placeable sensors, provides a new approach to the real-time MW detection, and could be developed further for use in MW-related investigations and interventions (such as mindfulness-based training of focused attention).

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

29 downloads since deposited on 04 Mar 2019
29 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Book Section, not_refereed, original work
Communities & Collections:04 Faculty of Medicine > Center of Competence Multimorbidity
08 Research Priority Programs > Dynamics of Healthy Aging
Dewey Decimal Classification:150 Psychology
Language:English
Date:23 February 2016
Deposited On:04 Mar 2019 10:40
Last Modified:25 Sep 2019 00:29
Publisher:Scitepress
ISBN:978-989-758-170-0
OA Status:Green
Free access at:Publisher DOI. An embargo period may apply.
Publisher DOI:https://doi.org/10.5220/0005702401980205

Download

Download PDF  'Automated Detection of Mind Wandering: A Mobile Application'.
Preview
Content: Published Version
Language: English
Filetype: PDF
Size: 501kB
View at publisher
Get full-text in a library